Update common_parse.py

magic_pdf/parse/common_parse.py

@@ -37,14 +37,15 @@ def process_file(file_path, pdf_ocr, excel_ocr, output_dir):
     """Process a single file for OCR based on its extension."""
     try:
         res = ''
+        start = time.time()
         if file_path.endswith('.pdf'):
 
             res = pdf_ocr.ocr_pdf_client(path=file_path, output_dir=output_dir)
         elif file_path.endswith('.xls') or file_path.endswith('.xlsx'):
             res = excel_ocr.parse(file_path, output_dir)
-
+        end = time.time()
         if res:
-            logger.info(f"文件处理成功，输出文件路径为: '{res}'")
+            logger.info(f"文件处理成功，输出文件路径为: '{res}', 耗时为：{end-start}")
         else:
             logger.warning(f"文件处理结果为空: '{file_path}'")
     except requests.exceptions.RequestException as req_err:
@@ -83,12 +84,19 @@ def main():
     config.read(args.config_path)
     pdf_server = config.get('server', 'pdf_server')
     pdf_ocr = ocrPdfClient(pdf_server)
-    excel_ocr = ExcelParser()
+    status = pdf_ocr.check_health()
+    if not status:
+        pdf_ocr = None
+        logger.warning(f'Health check failed. The server at "{pdf_server}" is not responding as expected.')
+        logger.info(f'文件解析服务无法正常运行')
+        return None
+    else:
+        excel_ocr = ExcelParser()
 
-    logger.info(f'输入目录或文件的路径为: {input_path}')
-    logger.info(f'输出目录为: {output_dir}')
+        logger.info(f'输入目录或文件的路径为: {input_path}')
+        logger.info(f'输出目录为: {output_dir}')
 
-    process_input(input_path, pdf_ocr, excel_ocr, output_dir)
+        process_input(input_path, pdf_ocr, excel_ocr, output_dir)
 
 
 if __name__ == "__main__":